计算机视觉——眼疾图片识别（数据集iChallenge-PM）
写在前面： 我是「虐猫人薛定谔i」，一个不满足于现状，有梦想，有追求的00后
\quad
本博客主要记录和分享自己毕生所学的知识，欢迎关注，第一时间获取更新。
\quad
不忘初心，方得始终。
\quad❤❤❤❤❤❤❤❤❤❤
文章目录
- 数据介绍
- 代码
- 结果
- 总结
数据介绍
百度大脑和中山大学中山眼科中心联合举办的iChallenge比赛提供了一系列医疗类数据集， 其中有一项是关于病理性近视(Pathologic Myopia，简称：PM)疾病的，iChallenge-PM
PALM-Training400该文件夹下存放的是训练用的图片
PALM-Validation400该文件夹下存放的是验证用的图片
label.csv文件（处理过了，原数据集中是excel文件，我把它转成csv文件了）
代码
LeNet网络结构
# 定义LeNet的网络结构
class LeNet(fluid.dygraph.Layer):
def __init__(self, name_scope, num_classes=1):
super(LeNet, self).__init__(name_scope)
self.conv1 = Conv2D(num_channels=3,
num_filters=6,
filter_size=5,
act='sigmoid')
self.pool1 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
self.conv2 = Conv2D(num_channels=6,
num_filters=16,
filter_size=5,
act='sigmoid')
self.pool2 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
self.conv3 = Conv2D(num_channels=16,
num_filters=120,
filter_size=4,
act='sigmoid')
self.fc1 = Linear(input_dim=300000, output_dim=64, act='sigmoid')
self.fc2 = Linear(input_dim=64, output_dim=num_classes)
def forward(self, x):
x = self.conv1(x)
x = self.pool1(x)
x = self.conv2(x)
x = self.pool2(x)
x = self.conv3(x)
x = fluid.layers.reshape(x, [x.shape[0], -1])
x = self.fc1(x)
x = self.fc2(x)
return x
AlexNet网络结构
# 定义AlexNet网络结构
class AlexNet(fluid.dygraph.Layer):
def __init__(self, name_scope, num_classes=1):
super(AlexNet, self).__init__(name_scope)
name_scope = self.full_name
self.conv1 = Conv2D(num_channels=3,
num_filters=96,
filter_size=11,
stride=4,
padding=5,
act='relu')
self.pool1 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
self.conv2 = Conv2D(num_channels=96,
num_filters=256,
filter_size=5,
stride=1,
padding=2,
act='relu')
self.pool2 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
self.conv3 = Conv2D(num_channels=256,
num_filters=384,
filter_size=3,
stride=1,
padding=1,
act='relu')
self.conv4 = Conv2D(num_channels=384,
num_filters=384,
filter_size=3,
stride=1,
padding=1,
act='relu')
self.conv5 = Conv2D(num_channels=384,
num_filters=256,
filter_size=3,
stride=1,
padding=1,
act='relu')
self.pool5 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
self.fc1 = Linear(input_dim=12544, output_dim=4096, act='relu')
self.drop_ratio1 = 0.5
self.fc2 = Linear(input_dim=4096, output_dim=4096, act='relu')
self.drop_ratio2 = 0.5
self.fc3 = Linear(input_dim=4096, output_dim=num_classes)
def forward(self, x):
x = self.conv1(x)
x = self.pool1(x)
x = self.conv2(x)
x = self.pool2(x)
x = self.conv3(x)
x = self.conv4(x)
x = self.conv5(x)
x = self.pool5(x)
x = fluid.layers.reshape(x, [x.shape[0], -1])
x = self.fc1(x)
x = fluid.layers.dropout(x, self.drop_ratio1)
x = self.fc2(x)
x = fluid.layers.dropout(x, self.drop_ratio2)
x = self.fc3(x)
return x
完整代码
import cv2
import os
import random
import numpy as np
import paddle.fluid as fluid
from paddle.fluid.dygraph.nn import Conv2D, Pool2D, Linear
"""
数据集iChallenge-PM（眼疾识别）
"""
def transform_img(img):
img = cv2.resize(img, (224, 224))
img = np.transpose(img, (2, 0, 1))
img = img.astype('float32')
img = img / 255.
img = img * 2.0 - 1.0
return img
def data_loader(datadir, batch_size=10, mode='train'):
filenames = os.listdir(datadir)
def reader():
if mode == 'train':
random.shuffle(filenames)
batch_imgs = []
batch_labels = []
for name in filenames:
filepath = os.path.join(datadir, name)
img = cv2.imread(filepath)
img = transform_img(img)
if name[0] == 'H':
label = 0
elif name[0] == 'N':
label = 0
elif name[0] == 'P':
label = 1
else:
print('Not excepted file name')
print(name[0])
exit(-1)
batch_imgs.append(img)
batch_labels.append(label)
if len(batch_imgs) == batch_size:
imgs_array = np.array(batch_imgs).astype('float32')
labels_array = np.array(batch_labels).astype(
'float32').reshape(-1, 1)
yield imgs_array, labels_array
batch_imgs = []
batch_labels = []
if len(batch_imgs) > 0:
imgs_array = np.array(batch_imgs).astype('float32')
labels_array = np.array(batch_labels).astype('float32').reshape(
-1, 1)
yield imgs_array, labels_array
return reader
def valid_data_loader(datadir, csvfile, batch_size=10, mode='valid'):
filelists = open(csvfile).readlines()
def reader():
batch_imgs = []
batch_labels = []
for line in filelists[1:]:
line = line.strip().split(',')
name = line[1]
label = int(line[2])
filepath = os.path.join(datadir, name)
img = cv2.imread(filepath)
img = transform_img(img)
batch_imgs.append(img)
batch_labels.append(label)
if len(batch_imgs) == batch_size:
imgs_array = np.array(batch_imgs).astype('float32')
labels_array = np.array(batch_labels).astype(
'float32').reshape(-1, 1)
yield imgs_array, labels_array
batch_imgs = []
batch_labels = []
if len(batch_imgs) > 0:
imgs_array = np.array(batch_imgs).astype('float32')
labels_array = np.array(batch_labels).astype('float32').reshape(
-1, 1)
yield imgs_array, labels_array
return reader
DATADIR = './res/PALM-Training400'
DATADIR2 = './res/PALM-Validation400'
CSCVFILE = './res/label.csv'
# 定义LeNet的网络结构
class LeNet(fluid.dygraph.Layer):
def __init__(self, name_scope, num_classes=1):
super(LeNet, self).__init__(name_scope)
self.conv1 = Conv2D(num_channels=3,
num_filters=6,
filter_size=5,
act='sigmoid')
self.pool1 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
self.conv2 = Conv2D(num_channels=6,
num_filters=16,
filter_size=5,
act='sigmoid')
self.pool2 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
self.conv3 = Conv2D(num_channels=16,
num_filters=120,
filter_size=4,
act='sigmoid')
self.fc1 = Linear(input_dim=300000, output_dim=64, act='sigmoid')
self.fc2 = Linear(input_dim=64, output_dim=num_classes)
def forward(self, x):
x = self.conv1(x)
x = self.pool1(x)
x = self.conv2(x)
x = self.pool2(x)
x = self.conv3(x)
x = fluid.layers.reshape(x, [x.shape[0], -1])
x = self.fc1(x)
x = self.fc2(x)
return x
# 定义AlexNet网络结构
class AlexNet(fluid.dygraph.Layer):
def __init__(self, name_scope, num_classes=1):
super(AlexNet, self).__init__(name_scope)
name_scope = self.full_name
self.conv1 = Conv2D(num_channels=3,
num_filters=96,
filter_size=11,
stride=4,
padding=5,
act='relu')
self.pool1 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
self.conv2 = Conv2D(num_channels=96,
num_filters=256,
filter_size=5,
stride=1,
padding=2,
act='relu')
self.pool2 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
self.conv3 = Conv2D(num_channels=256,
num_filters=384,
filter_size=3,
stride=1,
padding=1,
act='relu')
self.conv4 = Conv2D(num_channels=384,
num_filters=384,
filter_size=3,
stride=1,
padding=1,
act='relu')
self.conv5 = Conv2D(num_channels=384,
num_filters=256,
filter_size=3,
stride=1,
padding=1,
act='relu')
self.pool5 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
self.fc1 = Linear(input_dim=12544, output_dim=4096, act='relu')
self.drop_ratio1 = 0.5
self.fc2 = Linear(input_dim=4096, output_dim=4096, act='relu')
self.drop_ratio2 = 0.5
self.fc3 = Linear(input_dim=4096, output_dim=num_classes)
def forward(self, x):
x = self.conv1(x)
x = self.pool1(x)
x = self.conv2(x)
x = self.pool2(x)
x = self.conv3(x)
x = self.conv4(x)
x = self.conv5(x)
x = self.pool5(x)
x = fluid.layers.reshape(x, [x.shape[0], -1])
x = self.fc1(x)
x = fluid.layers.dropout(x, self.drop_ratio1)
x = self.fc2(x)
x = fluid.layers.dropout(x, self.drop_ratio2)
x = self.fc3(x)
return x
# 定义训练过程
def train(model):
with fluid.dygraph.guard():
print("---- start training ----")
model.train()
epoch_num = 5
opt = fluid.optimizer.Momentum(learning_rate=0.001,
momentum=0.9,
parameter_list=model.parameters())
train_loader = data_loader(DATADIR, batch_size=10, mode='train')
valid_loader = valid_data_loader(DATADIR2, CSCVFILE)
for epoch in range(epoch_num):
for batch_id, data in enumerate(train_loader()):
x_data, y_data = data
img = fluid.dygraph.to_variable(x_data)
label = fluid.dygraph.to_variable(y_data)
logits = model(img)
loss = fluid.layers.sigmoid_cross_entropy_with_logits(
logits, label)
avg_loss = fluid.layers.mean(loss)
if batch_id % 10 == 0:
print("epoch: {}, batch_id: {}, loss is: {}".format(
epoch, batch_id, avg_loss.numpy()))
avg_loss.backward()
opt.minimize(avg_loss)
model.clear_gradients()
model.eval()
accuracies = []
losses = []
for batch_id, data in enumerate(valid_loader()):
x_data, y_data = data
img = fluid.dygraph.to_variable(x_data)
label = fluid.dygraph.to_variable(y_data)
logits = model(img)
pred = fluid.layers.sigmoid(logits)
loss = fluid.layers.sigmoid_cross_entropy_with_logits(
logits, label)
pred2 = pred * (-1.0) + 1.0
pred = fluid.layers.concat([pred2, pred], axis=1)
acc = fluid.layers.accuracy(
pred, fluid.layers.cast(label, dtype='int64'))
accuracies.append(acc.numpy())
losses.append(loss.numpy())
print("[validation accuracy/loss: {}/{}]".format(
np.mean(accuracies), np.mean(losses)))
model.train()
fluid.save_dygraph(model.state_dict(), './result/iChallengePM')
fluid.save_dygraph(opt.state_dict(), './result/iChallengePM')
if __name__ == "__main__":
with fluid.dygraph.guard():
# model = LeNet("LeNet")
model = AlexNet("AlexNet")
train(model)
结果
LeNet网络的训练结果
---- start training ----
epoch: 0, batch_id: 0, loss is: [0.63386595]
epoch: 0, batch_id: 10, loss is: [0.69357824]
epoch: 0, batch_id: 20, loss is: [0.8262283]
epoch: 0, batch_id: 30, loss is: [0.70314413]
[validation accuracy/loss: 0.4725000262260437/0.6942468881607056]
epoch: 1, batch_id: 0, loss is: [0.69328773]
epoch: 1, batch_id: 10, loss is: [0.6822144]
epoch: 1, batch_id: 20, loss is: [0.6788982]
epoch: 1, batch_id: 30, loss is: [0.679153]
[validation accuracy/loss: 0.5275000333786011/0.6917198300361633]
epoch: 2, batch_id: 0, loss is: [0.66813517]
epoch: 2, batch_id: 10, loss is: [0.6962514]
epoch: 2, batch_id: 20, loss is: [0.6779094]
epoch: 2, batch_id: 30, loss is: [0.72074294]
[validation accuracy/loss: 0.5275000333786011/0.6916546821594238]
epoch: 3, batch_id: 0, loss is: [0.68267685]
epoch: 3, batch_id: 10, loss is: [0.69080985]
epoch: 3, batch_id: 20, loss is: [0.69051874]
epoch: 3, batch_id: 30, loss is: [0.7030691]
[validation accuracy/loss: 0.5275000333786011/0.6916455626487732]
epoch: 4, batch_id: 0, loss is: [0.70706123]
epoch: 4, batch_id: 10, loss is: [0.7118827]
epoch: 4, batch_id: 20, loss is: [0.72799003]
epoch: 4, batch_id: 30, loss is: [0.7123946]
[validation accuracy/loss: 0.5275000333786011/0.6917262077331543]
AlexNet网络的训练结果
---- start training ----
epoch: 0, batch_id: 0, loss is: [0.71437234]
epoch: 0, batch_id: 10, loss is: [0.66942436]
epoch: 0, batch_id: 20, loss is: [0.57675594]
epoch: 0, batch_id: 30, loss is: [0.5789426]
[validation accuracy/loss: 0.9100000262260437/0.5783206224441528]
epoch: 1, batch_id: 0, loss is: [0.59212446]
epoch: 1, batch_id: 10, loss is: [0.5880574]
epoch: 1, batch_id: 20, loss is: [0.4672559]
epoch: 1, batch_id: 30, loss is: [0.5209719]
[validation accuracy/loss: 0.9325000643730164/0.29782530665397644]
epoch: 2, batch_id: 0, loss is: [0.59152406]
epoch: 2, batch_id: 10, loss is: [0.2935087]
epoch: 2, batch_id: 20, loss is: [0.3406319]
epoch: 2, batch_id: 30, loss is: [0.21688469]
[validation accuracy/loss: 0.9375/0.21106351912021637]
epoch: 3, batch_id: 0, loss is: [0.09478948]
epoch: 3, batch_id: 10, loss is: [0.39397192]
epoch: 3, batch_id: 20, loss is: [0.34152466]
epoch: 3, batch_id: 30, loss is: [0.24933481]
[validation accuracy/loss: 0.9399999380111694/0.2010333091020584]
epoch: 4, batch_id: 0, loss is: [0.43089372]
epoch: 4, batch_id: 10, loss is: [0.06475895]
epoch: 4, batch_id: 20, loss is: [0.33812967]
epoch: 4, batch_id: 30, loss is: [0.12363017]
[validation accuracy/loss: 0.8949999809265137/0.282415509223938]
总结
AlexNet相比于LeNet，拥有更多的卷积层，并且激活函数使用的是ReLU，同时使用了dropout有效的防止模型出现过拟合现象。
通过运行结果可以看出，在眼疾筛查数据集iChallenge-PM上，LeNet的loss很难下降，模型没有收敛。而AlexNet的loss则能有效下降，并且识别的准确率能达到了90%以上。
蒟蒻写博客不易，加之本人水平有限，写作仓促，错误和不足之处在所难免，谨请读者和各位大佬们批评指正。
如需转载，请署名作者并附上原文链接，蒟蒻非常感激
名称：虐猫人薛定谔i
博客地址：https://blog.csdn.net/Deep___Learning